Yarn-dyed fabric defect detection based on U-shaped attention gate auto-encoder
张玥 1王世豪 1李英健 1刘帅波 1张宏伟1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 西安工程大学电子信息学院,陕西西安 710048
折叠
摘要
针对现有的基于自编码器和生成对抗网络的无监督深度学习算法在色织物缺陷检测任务中,存在普适性差、漏检率和误检率偏高等问题,提出一种U型注意力门自编码器(U-shaped at-tention gate auto-encoder,UAGAE)的色织物缺陷检测算法.首先,采用轻量化网络EfficientNet-B6作为特征提取模块来获取输入图像更具代表性的特征,通过引入注意力门(attention gate,AG)机制来抑制无关区域的特征响应,以解码器的特征作为参考剔除跳跃连接中的冗余信息来辅助图像重构;然后,在训练阶段使用组合的损失函数保证重构图像的结构和细节;最后,在检测阶段通过自适应阈值分割和数学形态学处理获得最终检测结果.所提算法在公共数据集YDFID-1上实现了 53.45％的准确率(precision,P)、61.58％的召回率(recall,R)、53.63％的分数(F1-measure,F1)和40.83％的平均交并比(intersection over union,IoU),在14个花型上实现了最佳的F1和IoU.对比实验结果表明,UAGAE算法相较于其他几种缺陷检测算法能够更好地完成色织物的缺陷检测与定位.
Abstract
The existing unsupervised deep learning algorithms based on auto-encoders and generative adversarial networks have problems such as poor generalizability,high missed and false detection rates in the defect detection task of yarn-dyed fabric.To address these issues,a yarn-dyed fabric defect detection algorithm based on U-shaped attention gate auto-encoder(UAGAE)is proposed.Firstly,the light weight network EfficientNet-B6 is employed as the feature extraction module to capture more representative features from input images.The introduced attention gate(AG)mechanism is used to suppress feature responses in non-target regions,leveraging decoder features as a reference to eliminate redundant information in skip connections,thereby aiding in image reconstruction.Subsequently,during the training phase,a combined loss function is utilized to preserve both the structure and details of the reconstructed images.Finally,during the detection phase,the ultimate detection results are obtained through adaptive threshold segmentation and mathematical morphology operations.The proposed algorithm achieves a precision(P)of 53.45％,recall(R)of 61.58％,F1-measure(F1)of 53.63％,and mean intersection over union(IoU)of 40.83％on the public dataset YDFID-1.Notably,it attains the highest F1 and IoU metrics across 14 different fabric patterns.The comparative experimental results indicate that the UAGAE algorithm,in comparison to several other defect detection algorithms,exhibits a superior capability in effectively performing yarn-dyed fabric defect detection and localization.
关键词
无监督深度学习/缺陷检测/注意力门(AG)机制/轻量化网络/图像重构/自适应阈值分割
Key words
unsupervised deep learning/defect detection/attention gate(AG)mechanism/lightweight network/image reconstruction/adaptive threshold segmentation
维普
万方数据